The autocorrelation (also known as serial correlation, serial dependence or mean aversion/mean reversion) of price changes (and therefore log returns) is insignificant. In light of the weak form of the efficient markets hypothesis, this is not surprising.
[daily]
"By contrast, for the absolute and squared returns, the autocorrelations start off at a moderate level (the first-order autocorrelation generally ranges between 0.2 and 0.3 for the stock returns and 0.1 and 0.2 for the exchange rate returns) but remain (significantly) positive for a substantial number of lags. In addition, the autocorrelation in the absolute returns is generally somewhat higher than the autocorrelation in the squared returns, especially for the stock market indices. This illustrates what has become known as the ‘Taylor property’ (see Taylor, 1986, pp. 52-5) - that is, when calculating the autocorrelations for the series |yt|δ| for various values of δ, one almost invariably finds that the autocorrelations are largest for δ = 1."
Frances and van Dijk (2000) page 30
[daily stock returns] "The autocorrelations in the absolute and squared return series are always much higher than those in the return series, and they are consistently significantly positive for lags up to 60 days. The autocorrelation between absolute returns, however, is generally higher than that in squared returns."
- CAMPBELL, John Y., Andrew W. LO and A. Craig MacKINLAY, 1996. The Econometrics of Financial Markets. [Cited by 1914] (329.05/year)
"The fact that the autocorrelations of daily, weekly, and monthly index returns in Table 2.4 are positive and often significantly different from zero..."
Campbell, Lo and MacKinlay (1996) page 68
"...411 individual securities, implying that there is negative serial correlation on average. For all stocks, the average serial correlation is -4%, and -5% for the smallest 100 stocks. However, the serial correlation is statistically and economically insignificant and provides little evidence against the random walk hypothesis. [...] These results are consistent with French and Roll’s (1986) finding that daily returns of individual securities are slightly negatively autocorrelated."
Campbell, Lo and MacKinlay (1996) page 72
"Nevertheless, the weak negative autocorrelations of the individual securities are an interesting contrast to the stronger positive autocorrelation of the portfolio returns."
Campbell, Lo and MacKinlay (1996) page 74
"Despite the fact that individual security returns are weakly negatively autocorrelated, portfolio returns—which are essentially averages of individual security returns—are strongly positively autocorrelated. This somewhat paradoxical result can mean only one thing: large positive cross-autocorrelations across individual securities across time."
Campbell, Lo and MacKinlay (1996) page 74
"In contrast to the positive serial correlation in daily, weekly, and monthly index returns documented by Lo and MacKinlay (1988) and others, Fama and French (1988b) and Poterba and Summers (1988) find negative serial correlation in multi-year index returns."
Campbell, Lo and MacKinlay (1996) page 78
- DEBONDT, W.F.M. and R. THALER, 1985. Does the stock market overreact. Journal of Finance. [Cited by 980] (47.09/year)
Abstract: "Research in experimental psychology suggests that, in violation of Bayes’ rule, most people tend to “overreact” to unexpected and dramatic news events. This study of market efficiency investigates whether such behavior affects stock prices. The empirical evidence, based on CRSP monthly return data, is consistent with the overreaction hypothesis. Substantial weak form market inefficiencies are discovered. The results also shed new light on the January returns earned by prior “winners” and “losers.” Portfolios of losers experience exceptionally large January returns as late as five years after portfolio formation."
- DACOROGNA, Michel M., et al., 2001. An introduction to high-frequency finance. books.global-investor.com. [Cited by 222] (46.09/year)
"Goodhart (1989) and Goodhart and Figliuoli (1991) first reported the existence of negative first-order autocorrelation of returns at the highest frequencies, which disappears once the price formation process is over. In Figure 5.1, the autocorrelation function of returns measured at a 1 min interval is plotted against its lags. The returns are computed using the previous tick interpolation. There is significant autocorrelation up to a lag of 4 min. For longer lags, the autocorrelations mainly lie within the 95% confidence interval of an identical and independent (i.i.d.) Gaussian distribution.
Dacorogna, et al. (2001) pages 123-124
"This negative autocorrelation is also seen in FX-rate transaction prices (Goodhart et al., 1995) and in Eurofutures contracts (Ballocchi et al. 1999b). For some stock indices such as the S&P 500, Bouchaud and Potters (2000) finds the autocorrelation of returns to be positive while it is not found in stock returns themselves or in futures contracts on indices (Ahn et al., 2000)."
Dacorogna, et al. (2001) page 124
- FAMA, Eugene F., 1970. Efficient Capital Markets: A Review of Theory and Empirical Work. The Journal of Finance, 25 383-417. [Cited by 1524] (42.54/year)
[there is no abstract on this paper]
- FRENCH, Kenneth R., G. William SCHWERT and Robert F. STAMBAUGH, 1987. Expected stock returns and volatility, Journal of Financial Economics, 19 (September 1987): 3-30. [Cited by 709] (37.66/year)
Abstract: "This paper examines the relation between stock returns and stock market volatility. We find evidence that the expected market risk premium (the expected return on a stock portfolio minus the Treasury bill yield) is positively related to the predictable volatility of stock returns. There is also evidence that unexpected stock market returns are negatively related to the unexpected change in the volatility of stock returns. This negative relation provides indirect evidence of a positive relation between expected risk premiums and volatility."
"Non-synchronous trading of securities causes daily portfolio returns to be autocorrelated, particularly at lag one [see Fisher (1966) and Scholes and Williams (1977)]."
- LO, A.W. and A.C. MACKINLAY, 1988. Stock market prices do not follow random walks: evidence from a simple specification test, Review of Financial Studies [Cited by 645] (35.83/year)
Abstract: "In this article we test the random walk hypothesis for weekly stock market returns by comparing variance estimators derived from data sampled at different frequencies. The random walk model is strongly rejected for the entire sample period (1962-1985) and for all subperiods for a variety of aggregate returns indexes and size-sorted portfolios. Although the rejections are due largely to the behavior of small stocks, they cannot be attributed completely to the effects of infrequent trading or time-varying volatilities. Moreover, the rejection of the random walk for weekly returns does not support a mean-reverting model of asset prices."
[CRSP index] "However, in contrast to the negative serial correlation that Fama and French (1987) found for longer-horizon returns, we find significant positive serial correlation for weekly and monthly holding-period returns."
"This empirical puzzle becomes even more striking when we show that autocorrelations of individual securities are generally negative." page 42
Lo and MacKinlay (1988)
- FAMA, E.F. and K.R. FRENCH, 1988. Permanent and Temporary Components of Stock Prices. The Journal of Political Economy. [Cited by 601] (33.76/year)
Abstract: "A slowly mean-reverting component of stock prices tends to induce negative autocorrelation in returns. The autocorrelation is weak for the daily and weekly holding periods common in market efficiency tests but stronger for long-horizon returns. In tests for the 1926-85 period, large negative autocorrelations for return horizons beyond a year suggest that predictable price variation due to mean reversion accounts for large fractions of 3 to 5-year return variances. Predictable variation is estimated to be about 40 percent of 3 to 5-year return variances for portfolios of small firms. The percentage falls to around 25 percent for portfolios of large firms."
"First-order autocorrelations of industry and decile portfolio returns for the 1926-85 period form a U-shaped pattern across increasing return horizons. The autocorrelations become negative for 2-year returns, reach minimum values for 3–5-year returns, and then move back toward 0.0 for longer return horizons. This pattern is consistent with the hypothesis that stock prices have a slowly decaying stationary componennt. The negative autocorrelation of returns generated by a slowly decaying component of prices is weak at the short return horizons common in empirical work, but it becomes stronger as the return horizon increases. Eventually, however, random-walk price components begin to dominate the variation of returns, and long-horizon autocorrelations move back toward 0.0."
"Finally, existing evidence (e.g., Fama and Schwert 1977; Keim and Stambaugh 1986; Fama and French 1987; French et al. 1987) suggests that expected returns are positively autocorrelated. The negative autocorrelation of long-horizon returns due to a stationary component of prices is consistent with positively autocorrelated expected returns."
- FRANSES, P.H. and D. DIJK, 2000. Non-Linear Time Series Models in Empirical Finance. books.google.com. [Cited by 196] (33.69/year)
[daily]
"By contrast, for the absolute and squared returns, the autocorrelations start off at a moderate level (the first-order autocorrelation generally ranges between 0.2 and 0.3 for the stock returns and 0.1 and 0.2 for the exchange rate returns) but remain (significantly) positive for a substantial number of lags. In addition, the autocorrelation in the absolute returns is generally somewhat higher than the autocorrelation in the squared returns, especially for the stock market indices. This illustrates what has become known as the ‘Taylor property’ (see Taylor, 1986, pp. 52-5) - that is, when calculating the autocorrelations for the series |yt|δ| for various values of δ, one almost invariably finds that the autocorrelations are largest for δ = 1."
Frances and van Dijk (2000) page 30
- FAMA, E.F. and K.R. FRENCH, 1988. Dividend Yields and Expected Stock Returns, Journal of Financial Economics, Volume 22, Issue 1 , October 1988, Pages 3-25. [Cited by 625] (33.21/year)
Abstract: "The power of dividend yields to forecast stock returns, measured by regression R2, increases with the return horizon. We offer a two-part explanation. (1) High autocorrelation causes the variance of expected returns to grow faster than the return horizon. (2) The growth of the variance of unexpected returns with the return horizon is attenuated by a discount-rate effect - shocks to expected returns generate opposite shocks to current prices. We estimate that, on average, the future price increases implied by higher expected returns are just offset by the decline in the current price. Thus, time-varying expected returns generate ‘temporary’ components of prices."
- ANDERSEN, T.G. and T. BOLLERSLEV, 1998. … Volatility: Intraday Activity Patterns, Macroeconomic Announcements, and Longer Run Dependencies. The Journal of Finance. [Cited by 257] (32.96/year)
"This paper characterizes the volatility in the DM-dollar foreign exchange market using an annual sample of five-minute returns. Our modeling approach explicitly captures the pronounced intraday activity patterns, the strong macroeconomic announcement effects, and the volatility persistence, or ARCH effects, familiar from lower frequency returns. The different features are separately quantified and shown, in conjunction, to account for a substantial fraction of the realized return variability, both at the intradaily and daily levels. Moreover, we demonstrate how the high frequency returns, when properly modeled, constitute an extremely valuable and vastly underutilized resource for better understanding the volatility dynamics at the daily or lower frequencies."
- LO, A.W. and A.C. MACKINLAY, 2001. A Non-Random Walk Down Wall Street. books.google.com. [Cited by 152] (31.54/year)
[market indices] "Our finding of positive autocorrelation for weekly holding-period returns differs from Fama and French’s (1988) finding of negative serial correlation for long holding-period returns. This positive correlation is significant not only for our entire sample period but also for all subperiods."
Lo and MacKinlay (1999) page 28
[market indices] "With a base interval of four weeks, we generally do not reject the random walk model even for the equal-weighted index. This is consistent with the relatively weak evidence against the random walk that previous studies have found when using monthly data."
Lo and MacKinlay (1999) page 29
[individual stocks] "The average variance ratio for individual securities is less than unity when q = 2, implying that there is negative serial correlation on average. For all stocks, the average serial correlation is -3 percent, and -6 percent for the smallest 100 stocks. However, the serial correlation is both statistically and economically insignificant and provides little evidence against the random walk hypothesis. [...] These results complement French and Roll’s (1986) finding that daily returns of individual securities are slightly negatively autocorrelated."
Lo and MacKinlay (1999) page 32
- BROCK, W., J. LAKONISHOK and B. LEBARON, 1992. Simple Technical Trading Rules and the Stochastic Properties of Stock Returns. The Journal of Finance. [Cited by 363] (26.31/year)
Abstract: "This paper tests two of the simplest and most popular trading rules--moving average and trading range break-by utilizing the Dow Jones Index from 1897 to 1986. Standard statistical analysis is extended through the use of bootstrap techniques. Overall, our results provide strong support for the technical strategies. The returns obtained from these strategies are not consistent with four popular null models: the random walk, the AR(1), the GARCH-M, and the Exponential GARCH. Buy signals consistently generate higher returns than sell signals, and further, the returns following buy signals are less volatile than returns following sell signals, and further, the returns following buy signals are less volatile than returns following sell signals. Moreover, returns following sell signals are negative, which is not easily explained by any of the currently existing equilibrium models."
"2Chopra, Lakonishok, and Ritter (1992), De Bondt and Thaler (1985), Fama and French (1986 [1988?]), and Poterba and Summers (1988) find negative serial correlation in returns of individual stocks and various portfolios over three- to ten-year intervals. Rosenberg, Reid, and Lanstein (1985) provide evidence for the presence of predictable return reversals on a monthly basis at the level of individual securities. Jegadeesh (1990) finds negative serial correlation for lags up to two months and positive serial correlation for longer lags. Lo and MacKinlay (1990a) report positive serial correlation in weekly returns for indexes and portfolios and a somewhat negative serial correlation for individual stocks. Lehmann (1990) and French and Roll (1986) report negative serial correlation at the level of individual securities for weekly and daily returns. Cutler, Poterba, and Summers (1990) present results from many asset markets generally supporting the hypothesis that returns are positively correlated at the horizon of several months and negatively correlated at the 3-to-5 year horizon."
[Dow index, daily returns] "Serial correlations are generally small with the exception of a few relatively large values at the first lag in the two most recent subperiods." [positive]
Brock, Lakonishok and LeBaron (1992)
- CONT, R., 2001. Empirical properties of asset returns: stylized facts and statistical issues. Quantitative Finance. [Cited by 123] (25.54/year)
Absence of autocorrelations: (linear) autocorrelations of asset returns are often insignificant, except for very small intraday time scales ( 20 minutes) for which microstructure effects come into play.
Cont (2001)
"5.1. Absence of linear autocorrelation It is a well-known fact that price movements in liquid markets do not exhibit any significant autocorrelation: the Figure 7. Autocorrelation function of tick by tick returns on KLM shares traded on the NYSE. Time scale: ticks. autocorrelation function of the price changes
C(τ) = corr(r(t,Δt), r(t + τ, Δt)) (14)
(where corr denotes the sample correlation) rapidly decays to zero in a few minutes (see figures 6 and 7): for τ ≥ 15 minutes it can be safely assumed to be zero for all practical purposes [21]. The absence of significant linear correlations in price increments and asset returns has been widely documented [43, 102] and is often cited as support for the ‘efficient market hypothesis’ [44]. The absence of correlation is intuitively easy to understand: if price changes exhibit significant correlation, this correlation may be used to conceive a simple strategy with positive expected earnings; such strategies, termed statistical arbitrage, will therefore tend to reduce correlations except for very short time scales, which represent the time the market takes to react to new information. This correlation time is typically several minutes for organized futures markets and even shorter for foreign exchange markets. Mandelbrot [85] expressed this property by stating that ‘arbitrage tends to whiten the spectrum of price changes’. This property implies that traditional tools of signal processing which are based on second-order properties, in the time domain—autocovariance analysis, ARMA modelling—or in the spectral domain—Fourier analysis, linear filtering—cannot distinguish between asset returns and white noise. This points out the need for nonlinear measures of dependence in order to characterize the dependence properties of asset returns.
In high-frequency return series of transaction prices, one actually observes a negative autocorrelation at very short lags (typically, one or a few trades). This is traditionally attributed to the bid-ask bounce [16]: transaction prices may take place either close to the ask or closer to the bid price and tend to bounce between these two limits. However, one also observes negative autocorrelations at the first lag in bid or ask prices themselves, suggesting a fast mean reversion of the price at the tick level. This feature may be attributed to the action of a market maker [47].
The absence of autocorrelation does not seem to hold systematically when the time scale Δt is increased: weekly and monthly returns do exhibit some autocorrelation. However given that the sizes of the data sets are inversely proportional to Δt the statistical evidence is less conclusive and more variable from sample to sample."
Cont (2001)
- PAGAN, A., 1996. The econometrics of financial markets, Journal of Empirical Finance, 3 15-102. [Cited by 247] (25.15/year)
Abstract: "The paper provides a survey of the work that has been done in financial econometrics in the past decade. It proceeds by first establishing a set of stylized facts that are characteristics of financial series and then by detailing the range of techniques that have been developed to model series which possess these characteristics. Both univariate and multivariate models are considered."
- BOUCHAUD, J.P. and M. POTTERS, 2000. Theory of financial risks, From Statistical Physics to Risk Management, Cambridge University Press, Cambridge. [Cited by 135] (23.20/year)
- LLORENTE, G., et al., 2002. Dynamic Volume-Return Relation of Individual Stocks, The Review of Financial Studies, Vol. 15, No. 4. (Autumn, 2002), pp. 1005-1047. [Cited by 83] (20.75/year)
Abstract: "We examine the dynamic relation between return and volume of individual stocks. Using a simple model in which investors trade to share risk or speculate on private information, we show that returns generated by risk-sharing trades tend to reverse themselves, while returns generated by speculative trades tend to continue themselves. We test this theoretical prediction by analyzing the relation between daily volume and first-order return autocorrelation for individual stocks listed on the NYSE and AMEX. We find that the cross-sectional variation in the relation between volume and return autocorrelation is related to the extent of informed trading in a manner consistent with the theoretical prediction."
"Many studies show that short-horizon returns of individual stocks exhibit negative autocorrelation [e.g., French and Roll (1986), Lo and MacKinlay (1988), Conrad, Kaul, and Nimalenndran (1991), Jegadeesh and Titman (1995), Canina et al. (1998)]. These autocorrelations are more pronounced in small stocks than in large stocks. French and Roll (1986) and Jegadeesh and Titman (1995) show that the first-order autocorrelation of daily returns is negative for small stocks, increases with the size of the firm, and is positive for large firms. The stocks in our sample exhibit similar return characteristics. The first-order autocorrelation of daily returns is negative for stocks with large bid-ask spreads (-0.088) and small sizes (-0.076). It is positive but very small for large stocks (0.003) and stocks with small bid-ask spreads (0.01).
Llorente, et al. (2002)
French and Roll (1986): "Stock Return Variances: The Arrival of Information and the Reaction of Traders" (24.20/year)
Jegadeesh and Titman (1995): "Short-Horizon Return Reversals and the Bid-Ask Spread" (3.84/year)
- CONRAD, J. and G. KAUL, 1998. An anatomy of trading strategies, Review of Financial Studies, 11, 489-519. [Cited by 165] (20.62/year)
Abstract: "In this article we use a single unifying framework to analyze the sources of profits to a wide spectrum of return-based trading strategies implemented in the literature. We show that less than 50% of the 120 strategies implemented in the article yield statistically significant profits and, unconditionally, momentum and contrarian strategies are equally likely to be successful. However, when we condition on the return horizon (short, medium, or long) of the strategy, or the time period during which it is implemented, two patterns emerge. A momentum strategy is usually profitable at the medium (3- to 12-month) horizon, while a contrarian strategy nets statistically significant profits at long horizons, but only during the 1926-1947 subperiod. More importantly, our results show that the cross-sectional variation in the mean returns of individual securities included in these strategies plays an important role in their profitability. The cross-sectional variation can potentially account for the profitability of momentum strategies and it is also responsible for attenuating the profits from price reversals to long-horizon contrarian strategies."
- DROST, F.C. and T.E. NIJMAN, 1993. Temporal Aggregation of Garch Processes. Econometrica. [Cited by 260] (20.32/year)
Abstract: "We derive low frequency, say weekly, models implied by high frequency, say daily, ARMA models with symmetric GARCH errors. Both stock and flow variable cases are considered. We show that low frequency models exhibit conditional heteroskedasticity of the GARCH form as well. The parameters in the conditional variance equation of the low frequency model depend upon mean, variance, and kurtosis parameters of the corresponding high frequency model. Moreover, strongly consistent estimators of the parameters in the high frequency model can be derived from low frequency data in many interesting cases. The common assumption in applications that rescaled innovations are independent is disputable, since it depends upon the available data frequency."
- FRENCH, K.R. and R. ROLL, 1986. Stock Return Variances: The Arrival of Information and the Reaction of Traders, Journal of Financial Economics. [Cited by 389] (19.65/year)
Abstract: "Asset prices are much more volatile during exchange trading hours than during non-trading hours. This paper considers three explanations for this phenomenon: (1) volatility is caused by public information which is more likely to arrive during normal business hours; (2) volatility is caused by private information which affects prices when informed investors trade; and (3) volatility is caused by pricing errors that occur during trading. Although a significant fraction of the daily variance is caused by mispricing, the behavior of returns around exchange holidays suggests that private information is the principle factor behind high trading-time variances."
- SCHOLES, M. and J. WILLIAMS, 1977. Estimating betas from nonsynchronous data, Journal of Financial Economics, Volume 5, Issue 3 , December 1977, Pages 309-327. [Cited by 547] (18.98/year)
Abstract: "Nonsynchronous trading of securities introduces into the market model a potentially serious econometric problem of errors in variables. In this paper properties of the observed market model and associated ordinary least squares estimators are developed in detail. In addition, computationally convenient, consistent estimators for parameters of the market model are calculated and then applied to daily returns of securities listed in the NYSE and ASE."
- GUILLAUME, D.M.D., et al., 1997. From the bird’s eye to the microscope: A survey of new stylized facts of the intra-daily foreign exchange markets. Finance and Stochastics. [Cited by 164] (18.60/year)
[FX] "4.2.1 Fact5: Negative first-order autocorrelation of the returns. Goodhart (1989) and Goodhart and Figliuoli (1991) first reported the existence of negative first-order autocorrelation of the price changes at the highest frequencies, which disappear once the price formation process is over. Goodhart(1989) also demonstrated that this negative auto-correlation is not affected by the presence (or absence) of major news announcements. Finally, Goodhart and Figliuoli (1992) showed that the resulting oscillations of the prices are not caused by bouncing prices between different geographical areas with different information sets. Note that this negative first-order auto-correlation of FXFX quotes is in constrast with the absence of such auto-correlation of real transaction prices, at least for the very small data sample studied in Goodhart et al.(1995).
A first explanation of this fact may be divergent opinions among traders. The convention alassumption that the FX market is composed of homogeneous traders who would share the same views about the effect of news, so that no correlation of the prices would be observed - or at most, a positive auto-correlation. However, traders have diverging opinions about the impact of news on the direction of prices. A second - and complementary - explanation for this negative auto-correlation is the tendency of market makers to skew the spread in a particular direction when they have order imbalances (Bollerslev and Domowitz 1993; Flood 1994). A third explanation is that even without order imbalances or diverging opinions on the price, certain banks systematically publish higher bid/ask spreads than other. This could also cause the ask (bid) prices to bounce back and forth between banks (Bollerslev and Melvin 1994)."
Guillaume, et al. (1997)
- JEGADEESH, N., 1990. Evidence of Predictable Behavior of Security Returns. The Journal of Finance. [Cited by 271] (17.15/year)
Abstract: "This paper presents new empirical evidence of predictability of individual stock returns. The negative first-order serial correlation in monthly stock returns is highly significant. Furthermore, significant positive serial correlation is found at longer lags, and the twelve-month serial correlation is particularly strong. Using the observed systematic behavior of stock returns, one-step-ahead return forecasts are made and ten portfolios are formed from the forecasts. The difference between the abnormal returns on the extreme decile portfolios over the period 1934-1987 is 2.49 percent per month."
- LO, Andrew W. and A. Craig MacKINLAY, 1990. When are Contrarian Profits Due to Stock Market Overreaction?, The Review of Financial Studies, Vol. 3, No. 2. (1990), pp. 175-205. [Cited by 250] (15.62/year)
Abstract: "If returns on some stocks systematically lead or lag those of others, a portfolio strategy that sells "winners" and buys "losers" can produce positive expected returns, even if no stock's returns are negatively autocorrelated as virtually all models of overreaction imply. Using a particular contrarian strategy we show that, despite negative autocorrelation in individual stock returns, weekly portfolio returns are strongly positively autocorrelated and are the result of important cross-autocorrelations. We find that the returns of large stocks lead those of smaller stocks, and we present evidence against overreaction as the only source of contrarian profits."
- GOODHART, C.A.E. and M. O'HARA. , 1997. High frequency data in financial markets: Issues and applications, Journal of Empirical Finance, 4 73-114. [Cited by 136] (15.41/year)
Abstract: "The development of high frequency data bases allows for empirical investigations of a wide range of issues in the financial markets. In this paper, we set out some of the many important issues connected with the use, analysis, and application of high-frequency data sets. These include the effects of market structure on the availability and interpretation of the data, methodological issues such as the treatment of time, the effects of intra-day seasonals, and the effects of time-varying volatility, and the information content of various market data. We also address using high frequency data to determine the linkages between markets and to determine the applicability of temporal trading rules. The paper concludes with a discussion of the issues for future research."
"The movement of prices following a trade is of obvious importance for
understanding the behavior of markets. In the standard sequential trade framework
(see Glosten and Milgrom, 1985, a market maker sets new trading prices equal to
the conditional expected value of the asset. The subsequent trading prices form a
martingale and, thus on an ex ante basis, prices and thus returns should be
uncorrelated. If the market maker cares about inventory, however, price changes
may be more complex, and in particular may exhibit negative serial correlation
due to the market maker's efforts to move his inventory position in a desired
direction. If the data do not allow complete differentiation between buy orders at
the ask and sell orders at the bid, then the first order negative auto-correlation of
returns will be accentuated by the bid-ask 'bounce' (Roll, 1984). Evidence of such
negative auto-correlation would be more visible the higher the frequency of the
data.
In electronic markets, or in specialist markets permitting limit orders, price
movements may be affected by the clearing of orders against existing orders. In
particular, a large order may move along the limit order book, and/or transact
with a number of competing market makers. Rather than display the negative first
order correlation in returns, trades and quotes noted above, this can result in
positive auto-correlation in these variables. Again such effects would, one would
expect, be more prominent the higher the frequency of the data.
As elsewhere, there is more empirical evidence on auto-correlations in the
NYSE than elsewhere. Due to the nature of the data, most studies have been
undertaken on a trade by trade basis without knowing precisely whether the active
side of the trade was a buy or a sell. Consequently such results incorporate some
bias due to the 'bounce' between the bid and the ask (see for example Porter, 1992
and Harris, 1986). After taking account of this effect, the latest findings suggest
quite strong signs of positic, e auto-correlation in trades (i.e. a trade at the ask is
more likely to be followed by another at the ask) (see Huang and Stoll, 1994;
Madhavan et al., 1994; Easley et al., 1995; Hasbrouck, 1991a,b, 1988; Hasbrouck
and Ho, 1987, and (relatively much weaker) in returns, Hasbrouck and Ho, 1987;
Lo and MacKinley, 1988). The auto-correlation of trades varies, however, accord-
ing to whether the stock has a low trade volume, in which case the negative
auto-correlation implied by inventory control effects reappears, or a high volume,
in which case positive auto-correlation dominates (Hasbrouck, 1988). Hasbrouck
(1988) suggests that this positive auto-correlation arises because the NYSE
combines a limit order procedure, where one would expect positive auto-correla-
tion, with a specialist, where one would not ~-~t; thus this positive autocorrelation
"is perhaps a consequence of the relatively greater importance for these stocks of
public limit orders and relatively lesser importance of specialist transactions."
In the forex market, the only available time series providing data on trades and
quotes are the very short series for small and possibly unrepresentative parts of the
market obtained by Lyons (1993a,b), Lyons (1994) and by Goodhart et al. (1994).
The latter report very strong positive autocorrelation in trades (buys following
buys), but approximate random walk in returns. There is, on the other hand, now a
huge data set available of Reuters FXFX indicative quotes. At intervals shorter
than ten minutes, or on a tick by tick basis, these show strong signs of a first order
moving average negative auto-correlation (Goodhart, 1989; Goodhart and Figli-
uoli, 1991; Goodhart and Giugale, 1993; Baillie and Bollerslev, 1990a,b). Most
authors ascribe this to the indicative nature of the FXFX quote series, with quotes
shifting backwards and forwards between banks with differing order imbalances,
persistent tendencies to quote high or low (Bollerslev and Domowitz, 1993), or
differing information sets (Goodhart and Figliuoli, 1992). Goodhart et al. (1994)
report, however, that negative auto-correlation in quotes remains present in their
short, partial series of firm quote data. Goodhart and Payne (1995, forthcoming)
ascribe this, along the lines of the theoretical analysis of Ho and Stoll (1983), to
the existence of 'thin' markets, so that when the best quote is removed by a trade,
the next best price is some distance behind that.
Whatever the reasons, the empirical findings of c'ery high frequency autocorre-
lations (strong positive in trades; perhaps weak positive, after taking account of
the bounce, in returns; and negative in quotes) are an interesting feature of high
frequency data series. Another interesting inter-relationship is that between trades
and quotes (and hence spreads as well), which has been developed in pioneering
work by Hasbrouck (1991a,b) using data from the NYSE. He finds that the full
impact of a trade on the price occurs with a protracted lag, and that as a function
of trade size, the innovation on the quote is non-linear, positive and increasing, but
concave. Further, he finds that spread size exhibits a response to trading activity,
with large trades associated with a widening of the spread. Moreover, trades
occurring when spreads are relatively wider have a greater impact than when
spreads are narrow. Intriguingly, he argues that the price impact and (by implica-
tion) the extent of the information asymmetry appear more significant for firms
with smaller market values.
Goodhart et al. (1994) in a similar study using FX data find that knowing the
quantity involved in each trade added little (in their case nothing) to the informa-
tion obtained from the direction of trade, a result consistent with the earlier
mentioned works of Easley et al. (1995) and Jones et al. (1994). In contrast to
Hasbrouck, Goodhart et al. found no significant effect of quote revision on order
flow, since the frequency of quote revision, rather than the size of each quote
revision, appears to be the crucial variable determining the likelihood of future
trades."
- LEWELLEN, Jonathan, 2002. Momentum and Autocorrelation in Stock Returns, The Review of Financial Studies, Vol. 15, No. 2, Special Issue: Conference on Market Frictions and Behavioral Finance (2002), pp. 533-563.
[Cited by 58] (15.21/year)
Abstract: "This article studies momentum in stock returns, focusing on the role of industry, size, and book-to-market (B/M) factors. Size and B/M portfolios exhibit momentum as strong as that in individual stocks and industries. The size and B/M portfolios are well diversified, so momentum cannot be attributed to firm- or industry-specific returns. Further, industry, size, and B/M portfolios are negatively autocorrelated and cross-serially correlated over intermediate horizons. The evidence suggests that stocks covary "too strongly" with each other. I argue that excess covariance, not underreaction, explains momentum in the portfolios."
- KEIM, Donald B. and Robert F. STAMBAUGH, 1986. Predicting Returns in the Stock and Bond Markets, Journal of Financial Economics 17 (December 1986): 357-90. [Cited by 301] (15.19/year)
Abstract: "Several predetermined variables that reflect levels of bond and stock prices appear to predict returns on common stocks of firms of various sizes, long-term bonds of various default risks, and default-free bonds of various maturities. The returns on small-firm stocks and low-grade bonds are more highly correlated in January than in the rest of the year with previous levels of asset prices, especially prices of small-firm stocks. Seasonality is found in several conditional risk measures, but such seasonality is unlikely to explain, and in some cases is opposite to, the seasonal found in mean returns."
- ROLL, R., 1984. A Simple Implicit Measure of the Effective Bid-Ask Spread in an Efficient Market, The Journal of Finance, Vol. 39, No. 4, 1127-1139. [Cited by 331] (15.17/year)
Abstract: "In an efficient market, the fundamental value of a security fluctuates randomly. However, trading costs induce negative serial dependence in successive observed market price changes. In fact, given market efficiency, the effective bid-ask spread can be measured by
Spread = 2v-cov
where "cov" is the first-order serial covariance of price changes. This implicit measure of the bid-ask spread is derived formally and is shown empirically to be closely related to firm size."
- ALEXANDER, C., 2001. Market Models: A Guide to Financial Data Analysis. Wiley. [Cited by 71] (14.74/year)
"The autocorrelation properties of high-frequency returns have been established by a large empirical literature:
- There is little autocorrelation in returns, except perhaps some negative autocorrelation at very high frequency (Goodhart and Figliouli, 1991; Bollerslev and Domowitz, 1993; Zhou, 1992 [?]).
- There is, however, a lot of autocorrelation in squared returns, and this conditional heteroscedasticity becomes more pronounced as the sampling frequency increases (Andersen and Bollerslev, 1996 [1998]; Baillie and Bollerslev, 1990 [1991]; Zhou, 1996; Drost and Nijman, 1993; Ghose and Kroner, 1995; Taylor and Xu, 1997)."
Alexander (2001), pages 391-392
"Not all market returns are autocorrelated; it depends not only on the frequency of the return, but also on the time period of measurement and, of course, on the market itself [...]. However, daily returns to equity indices often do exhibit some autocorrelation. A possible cause of autocorrelation in equity indices is the news arrival process, where new information affects trading in some stocks before others. When daily returns are autocorrelated this may be caused by news arriving in the market during the afternoon, which affects only those stocks which are traded late in the day. The prices of other stocks in the index will not be affected until they are traded on the next or subsequent days. Important international news is likely to affect the stock indices of different countries in the same way.
Alexander (2001), page 385
- COOPER, Michael J., Roberto C. GUTIERREZ and Allaudeen HAMEED, 2004. Market States and Momentum. The Journal of Finance, Volume 59 Issue 3, Page 1345. [Cited by 26] (14.31/year)
Abstract: "We test overreaction theories of short-run momentum and long-run reversal in the cross section of stock returns. Momentum profits depend on the state of the market, as predicted. From 1929 to 1995, the mean monthly momentum profit following positive market returns is 0.93%, whereas the mean profit following negative market returns is -0.37%. The up-market momentum reverses in the long-run. Our results are robust to the conditioning information in macroeconomic factors. Moreover, we find that macroeconomic factors are unable to explain momentum profits after simple methodological adjustments to take account of microstructure concerns."
"fast decay of the autocorrelation of price changes."
Johnson, Jefferies and Hui (2003), page 69
"slow decay of the autocorrelation of absolute value of price-changes"
Johnson, Jefferies and Hui (2003), page 69
- slow decay of the autocorrelation of absolute value of price-changes
- fast decay of the autocorrelation of price changes."
Johnson, Jefferies and Hui (2003), page 69
- JOHNSON, N.F., et al., 2003. Financial Market Complexity: What Physics Can Tell Us about Market Behaviour. books.google.com. [Cited by 40] (14.19/year)
- LEHMANN, B., 1990. Fads, Martingales, and Market Efficiency. [Cited by 220] (13.93/year)
Abstract: "Predictable variation in equity returns might reflect either (1) predictable changes in expected returns or (2) market inefficiency and stock price "overreaction." These explanations can be distinguished by examining returns over short time intervals since systematic changes in fundamental valuation over intervals like a week should not occur in efficient markets. The evidence suggests that the "winners" and "losers" one week experience sizeable return reversals the next week in a way that reflects apparent arbitrage profits which persist after corrections for bid-ask spreads and plausible transactions costs. This probably reflects inefficiency in the market for liquidity around large price changes."
- MCINISH, T.H. and R.A. WOOD, 1992. An Analysis of Intraday Patterns in Bid/Ask Spreads for NYSE Stocks. The Journal of Finance. [Cited by 191] (13.83/year)
Abstract: "The behavior of time-weighted bid-ask spreads over the trading day are examined. The plot of minute-by-minute spreads versus time of day has a crude reverse J-shaped pattern. Schwartz identifies four determinants of spreads: activity, risk, information, and competition. Using a linear regression model, a significant relationship between these same factors and intraday spreads is demonstrated, but dummy variables for time of day have a reverse J-shape. For given values of the activity, risk, information and competition measures, spreads are higher at the beginning and end of the day relative to the interior period."
- LONGIN, Francois M., 1996. The Asymptotic Distribution of Extreme Stock Market Returns, The Journal of Business, Vol. 69, No. 3. (Jul., 1996), pp. 383-408. [Cited by 126] (12.83/year)
Abstract: "This article presents a study of extreme stock market price movements. According to extreme value theory, the form of the distribution of extreme returns is precisely known and independent of the process generating returns. Using data for an index of the most traded stocks on the New York Stock Exchange for the period 1885-1990, I show empirically that the extreme returns obey a Fréchet distribution."
[daily observations of an index of the most traded stocks]
The first-order autocorrelation is small (0.047) but significantly positive. Litle serial correlation is found at higher lags. For the second moment, a strong positive serial correlation (0.229 at lag 1) is found, which suggests ARCH effects."
Longin (1996)
- FARMER, J.D., 1999. Physicists attempt to scale the ivory towers of finance. Computing in Science and Engineering. [Cited by 84] (12.32/year)
"[...] the autocorrelation of log-returns is typically very close to zero for times longer than about 15 to 30 minutes."
Farmer (1999)
- FAMA, E. F. and G. W. SCHWERT, 1977. Asset returns and inflation, Journal of Financial Economics, 5, 115-146. [Cited by 347] (12.04/year)
Abstract: "We estimate the extent to which various assets were hedges against the expected and unexpected components of the inflation rate during the 1953–1971 period. We find that U.S. government bonds and bills were a complete hedge against expected inflation, and private residential real estate was a complete hedge against both expected and unexpected inflation. Labor income showed little short-term relationship with either expected or unexpected inflation. The most anomalous result is that common stock returns were negatively related to the expected component of the inflation rate, and probably also to the unexpected component."
- AKGIRAY, V., 1989. Conditional Heteroscedasticity in Time Series of Stock Returns: Evidence and Forecasts, The Journal of Business, Vol. 62, No. 1. (Jan., 1989), pp. 55-80. [Cited by 196] (11.66/year)
Abstract: "This article presents new evidence about the time-series behavior of stock prices. Daily return series exhibit significant levels of second-order dependence, and they cannot be modeled as linear white-noise processes. A reasonable return-generating process is empirically shown to be a first-order autoregressive process with conditionally heteroscedastic innovations. In particular, generalized autoregressive conditional heteroscedastic GARCH (1, 1) processes fit to data very satisfactorily. Various out-of-sample forecasts of monthly return variances are generated and compared statistically. Forecasts based on the GARCH model are found to be superior."
[daily stock returns] "Daily return series exhibit significant levels of second-order dependence, and they cannot be modeled as linear white-noise processes. A reasonable return-generating process is empirically shown to be a first-order autoregressive process with conditionally heteroscedastic innovations."
[daily stock returns] "The conclusion must be that daily return series are not made up of independent variates."
[daily stock returns] "The return series display high first-lag auto correlations (ranging from 0.18 in period 4 to 0.31 in period 2) and apparently insignificant autocorelations at longer lags."
[daily stock returns] "The autocorrelations in the absolute and squared return series are always much higher than those in the return series, and they are consistently significantly positive for lags up to 60 days. The autocorrelation between absolute returns, however, is generally higher than that in squared returns."
[daily stock returns] "...the autocorrelations in the series of equal-weighted index returns are generally higher than those in the value-weighted series."
Akgiray (1989)
- CHAN, N., et al., 2005. Systemic Risk and Hedge Funds. [Cited by 9] (11.02/year)
Abstract: "Systemic risk is commonly used to describe the possibility of a series of correlated defaults among nancial institutions—typically banks—that occur over a short period of time, often caused by a single major event. However, since the collapse of Long Term Capital Management in 1998, it has become clear that hedge funds are also involved in systemic risk exposures. The hedge-fund industry has a symbiotic relationship with the banking sector, and many banks now operate proprietary trading units that are organized much like hedge funds. As a result, the risk exposures of the hedge-fund industry may have a material impact on the banking sector, resulting in new sources of systemic risks. In this paper, we attempt to quantify the potential impact of hedge funds on systemic risk by developing a number of new risk measures for hedge funds and applying them to individual and aggregate hedge-fund returns data. These measures include: illiquidity risk exposure, nonlinear factor models for hedge-fund and banking-sector indexes, logistic regression analysis of hedge-fund liquidation probabilities, and aggregate measures of volatility and distress based on regime-switching models. Our preliminary findings suggest that the hedge-fund industry may be heading into a challenging period of lower expected returns, and that systemic risk is currently on the rise."
"In comparison to the S&P 500, which has a first-order autocorrelation coefficient of -1.0%, ..."
Chan et al., 2005
Systemic Risk and Hedge Funds
- CHOPRA, N., J. LAKONISHOK and J.R. RITTER, 1992. Measuring abnormal performance: Do stocks overreact. Journal of Financial Economics, Volume 31, Issue 2, Pages 235-268. [Cited by 148] (10.73/year)
Abstract: "A highly controversial issue in financial economies is whether stocks overreact. In this paper we find an economically-important overreaction effect even after adjusting for size and beta. In portfolios formed on the basis of prior five-year returns, extreme prior losers outperform extreme prior winners by 5–10% per year during the subsequent five years. Although we find a pronounced January seasonal, our evidence suggests that the overreaction effect is distinct from tax-loss selling effects. Interestingly, the overreaction effect is substantially stronger for smaller firms than for larger firms. Returns consistent with the overeaction hypothesis are also observed for short windows around quarterly earnings announcements."
- CECCHETTI, Stephen G., Pok-Sang LAM and Nelson C. MARK, 1990. Mean Reversion in Equilibrium Asset Prices, The American Economic Review, Vol. 80, No. 3. (Jun., 1990), pp. 398-418. [Cited by 169] (10.69/year)
Abstract: "This paper demonstrates that negative serial correlation in long horizon stock returns is consistent with an equilibrium model of asset pricing. When investors display only a moderate desire to smooth their consumption, commonly used measures of mean reversion in stock prices calculated from historical returns data nearly always lie within a 60 percent confidence interval of the median of the Monte Carlo distributions implied by our equilibrium model. From this evidence, we conclude that the degree of serial correlation in the data could plausibly have been generated by our model."
- ZHOU, Bin, 1996. High-Frequency Data and Volatility in Foreign-Exchange Rates. Journal of Business & Economic Statistics, Vol. 14, No. 1. (Jan., 1996), pp. 45-52. [Cited by 101] (10.31/year)
Abstract: "Exchange rates, like many other financial time series, display substantial heteroscedasticity. This poses obstacles in detecting trends and changes. Understanding volatility becomes extremely important in studying financial time series. Unfortunately, estimating volatility from low-frequency data, such as daily, weekly, or monthly observations, is very difficult. The recent availability of ultra-high-frequency observations, such as tick-by-tick data, to large financial institutions creates a new possibility for the analysis of volatile time series. This article uses tick-by-tick foreign-exchange rates to explore this new type of data. Unlike low-frequency data, high-frequency data have extremely high negative first-order autocorrelation in their return. In this article, I propose a model that can explain the negative autocorrelation and a volatility estimator for high-frequency data. The daily and hourly volatility estimates of exchange rate show some interesting patterns."
- ONNELA, J.P., et al., 2003. Dynamics of market correlations: Taxonomy and portfolio analysis, Physical Review E 68, 056110. [Cited by 26] (10.15/year)
Abstract: "The time dependence of the recently introduced minimum spanning tree description of correlations between stocks, called the ``asset tree'' have been studied to reflect the economic taxonomy. The nodes of the tree are identified with stocks and the distance between them is a unique function of the corresponding element of the correlation matrix. By using the concept of a central vertex, chosen as the most strongly connected node of the tree, an important characteristic is defined by the mean occupation layer (MOL). During crashes the strong global correlation in the market manifests itself by a low value of MOL. The tree seems to have a scale free structure where the scaling exponent of the degree distribution is different for `business as usual' and `crash' periods. The basic structure of the tree topology is very robust with respect to time. We also point out that the diversification aspect of portfolio optimization results in the fact that the assets of the classic Markowitz portfolio are always located on the outer leaves of the tree. Technical aspects like the window size dependence of the investigated quantities are also discussed."
- ROSENBERG, B., K. REID and R. LANSTEIN, 1985. Persuasive evidence of market inefficiency, Journal of Portfolio Management. [Cited by 209] (10.04/year)
Abstract: "The article evaluates the performance of the book/price and specific-return-reversal strategies in detecting stock market inefficiency. In book/price strategy, the strategy buys stocks with a high ratio of book value of common equity per share to market price per share and sells stocks with a low book/price. The specific-return-reversal strategy calculates the difference between the investment return for the previous month on the stock and a fitted value for that return based upon common factors in the stock market in the previous month. Both strategies independently achieved highly significant results, which were consistent with their prior performance in the retrospective study. The success of two such diverse instrumental variables in detecting market inefficiency suggests that there are still larger potential profits to be made provided that the security analyst can identify the valuation errors that correlate with these instruments."
- BAILLIE, R.T. and T. BOLLERSLEV, 1994. Cointegration, Fractional Cointegration, and Exchange Rate Dynamics, The Journal of Finance. [Cited by 116] (9.82/year)
Abstract: "Multivariate tests due to Johansen (1988, 1991) as implemented by Baillie and Bollerslev (1989a) and Diebold, Gardeazabal, and Yilmaz (1994) reveal mixed evidence on whether a group of exchange rates are cointegrated. Further analysis of the deviations from the cointegrating relationship suggests that it possesses long memory and may possibly be well described as a fractionally integrated process. Hence, the influence of shocks to the equilibrium exchange rates may only vanish at very long horizons."
- TAYLOR, S.J. and X. XU, 1997. The incremental volatility information in one million foreign exchange quotations, Journal of Empirical Finance [Cited by 83] (9.43/year)
Abstract: "The volatility information found in high-frequency exchange rate quotations and in implied volatilities is compared by estimating ARCH models for DM/$ returns. Reuters quotations are used to calculate five-minute returns and hence hourly and daily estimates of realised volatility that can be included in equations for the conditional variances of hourly and daily returns. The ARCH results show that there is a significant amount of information in five-minute returns that is incremental to options information when estimating hourly variances. The same conclusion is obtained by an out-of-sample comparison of forecasts of hourly realised volatility."
- LIU, Y., et al., 1997. Correlations in Economic Time Series. Arxiv preprint cond-mat/9706021. [Cited by 80] (9.01/year)
Abstract: "A financial index of the New York stock exchange, the S&P500, is analyzed at 1 min intervals over the 13yr period, January 84-December 96. We quantify the correlations of the absolute values of the index increment. We find that these correlations can be described by two different power laws with a crossover time tx ~ 600min. Detrended fluctuation analysis gives exponents ~ -- 0.66 and ~2 ~--- 0.93 for t < t× and t > t×, respectively. Power spectrum analysis gives corresponding exponents fll = 0.31 and f12 = 0.90 for f > f× and f < f×, respectively."
- GETMANSKY, M., A.W. LO and I. MAKAROV, 2003. An Econometric Model of Serial Correlation and Illiquidity in Hedge Fund Returns. [Cited by 22] (8.35/year)
Abstract: "The returns to hedge funds and other alternative investments are often highly serially correlated in sharp contrast to the returns of more traditional investment vehicles such as long-only equity portfolios and mutual funds. In this paper, we explore several sources of such serial correlation and show that the most likely explanation is illiquidity exposure, i.e., investments in securities that are not actively traded and for which market prices are not always readily available. For portfolios of illiquid securities, reported returns will tend to be smoother than true economic returns, which will understate volatility and increase risk-adjusted performance measures such as the Sharpe ratio. We propose an econometric model of illiquidity exposure and develop estimators for the smoothing profile as well as a smoothing-adjusted Sharpe ratio. For a sample of 908 hedge funds drawn from the TASS database, we show that our estimated smoothing coefficients vary considerably across hedge-fund style categories and may be a useful proxy for quantifying illiquidity exposure."
- SIAS, R.W. and L.T. STARKS, 1997. Return autocorrelation and institutional investors, Journal of Financial Economics, Volume: 46, Issue (Month): 1 (October) pages 103-131. [Cited by 72] (8.34/year)
Abstract: "We propose and test the hypothesis that trading by institutional investors contributes to serial correlation in daily returns. Our results demonstrate that NYSE particles and individual security daily return autocorrelationsare an increasing function of the level of institutional ownership. Moreover, the results are consistent with the hypothesis that institutional trading reflects information and increases the speed of price adjustment. The relation between autocorrelation and institutional holdings does not, however, apparent to be driven by market frictions or rational time-varying required rates of return. We conclude that institutional investors correlated trading patterns contribute to axial correlation in daily returns."
- BOLLERSLEV, T. and I. DOMOWITZ, 1993. Trading Patterns and Prices in the Interbank Foreign Exchange Market. The Journal of Finance. [Cited by 105] (8.21/year)
Abstract: "The behavior of quote arrivals and bid-ask spreads is examined for continuously recorded deutsche mark-dollar exchange rate data over time, across locations, and by market participants. A pattern in the intraday spread and intensity of market activity over time is uncovered and related to theories of trading patterns. Models for the conditional mean and variance of returns and bid-ask spreads indicate volatility clustering at high frequencies. The proposition that trading intensity has an independent effect on returns volatility is rejected but holds for spread volatility. Conditional returns volatility is increasing in the size of the spread."
- WOOD, R.A., T.H. MCINISH and J.K. ORD, 1985. An Investigation of Transactions Data for NYSE Stocks. The Journal of Finance 40, 723-739. [Cited by 171] (8.21/year)
- KIM, M.J., C.R. NELSON and R. STARTZ, 1991. Mean Reversion in Stock Prices? A Reappraisal of the Empirical Evidence, The Review of Economic Studies, Vol. 58, No. 3, Special Issue: The Econometrics of Financial Markets. (May, 1991), pp. 515-528. [Cited by 117] (7.90/year)
Abstract: "The paper re-examines the empirical evidence for mean-reverting behaviour in stock prices. Comparison of data before and after World War II shows that mean reversion is entirely a pre-war phenomenon. Using randomization methods to calculate significance levels, we find that the full sample evidence for mean reversion is weaker than previously indicated by Monte Carlo methods under a Normal assumption. Further, the switch to mean-averting behaviour after the war is about to be too strong to be compatible with sampling variation. We interpret these findings as evidence of a fundamental change in the stock returns process and conjecture that it may be due to the resolution of the uncertainties of the 1930's and 1940's."
- CHUI, A.C.W. and C.C.Y. KWOK, 1998. Cross-autocorrelation Between A Shares and B Shares in the Chinese Stock Market. JOURNAL OF FINANCIAL RESEARCH. [Cited by 57] (7.46/year)
Abstract: "Listed companies in China upon meeting certain requirements can issue two types of shares: A shares and B shares. Local investors in China can only buy and sell A shares, while foreign investors can only trade B shares. We argue that foreign investors may receive news about China faster than domestic Chinese investors because of information barriers currently existing in China. Since foreigners participate in the B-share market, the price movements of B shares will thus reflect the common information that the foreigners have. Rational A-share investors can therefore condition their trading decisions on the previous price movements of B shares. As a result, returns on B shares lead the returns on A shares. Using daily prices of A and B shares, we demonstrate that returns of B shares are correlated with those of A shares and that this correlation depends on the information transmission mechanism at work. The pattern of the asymmetric cross-autocorrelation is robust to the inclusion of the lagged realized returns and the trading volumes."
- HASBROUCK, J., 1988. Trades, quotes, inventories, and information. Journal of Financial Economics, 22,
229-252. [Cited by 132] (7.41/year)
- BAILLIE, R.T. and T. BOLLERSLEV, 1991. Intra-Day and Inter-Market Volatility in Foreign Exchange Rates. The Review of Economic Studies, Vol. 58, No. 3, Special Issue: The Econometrics of Financial Markets. (May, 1991), pp. 565-585. [Cited by 109] (7.37/year)
Abstract: "Four foreign exchange spot rate series, recorded on an hourly basis for a six-month period in 1986 are examined. A seasonal GARCH model is developed to describe the time-dependent volatility apparent in the percentage nominal return of each currency. Hourly patterns in volatility are found to be remarkably similar across currencies and appear to be related to the opening and closing of the worlds major markets. Robust LM tests designed to deal with the extreme leptokurtosis in the data fails to uncover any evidence of misspecification or the presence of volatility spillover effects between the currencies or across markets."
- JAIN, P.C. and G.H. JOH, 1988. The Dependence between Hourly Prices and Trading Volume, The Journal of Financial and Quantitative Analysis, Vol. 23, No. 3. (Sep., 1988), pp. 269-283.
[Cited by 130] (7.30/year)
Abstract: "This study provides evidence on joint characteristics of hourly common stock trading volume and returns on the New York Stock Exchange. Average volume traded shows significant differences across trading hours of the day and across days of the week. Average returns differ across hours of the day, and, to some extent, across days of the week. There is a strong contemporaneous relation between trading volume and returns and also a relation between trading volume and returns lagged up to four hours. Furthermore, the trading volume-returns relation is steeper for positive returns than for nonpositive returns."
- POTERBA, J. and L. SUMMERS, 1988. Mean reversion in stock returns: Evidence and implications. Journal of Financial Economics. [Cited by 123] (6.91/year)
Abstract: "This paper investigates transitory components in stock prices. After showing that statistical tests have little power to detect persistent deviations between market prices and fundamental values, we consider whether prices are mean-reverting, using data from the United States and 17 other countries. Our point estimates imply positive autocorrelation in returns over short horizons and negative autocorrelation over longer horizons, although random-walk price behavior cannot be rejected at conventional statistical levels. Substantial movements in required returns are needed to account for these correlation patterns. Persistent, but transitory, disparities between prices and fundamental values could also explain our findings."
- KEANE, M.P. and D.E. RUNKLE, 1992. On the Estimation of Panel-Data Models with Serial Correlation When Instruments Are Not Strictly Exogenous. Journal of Business & Economic Statistics, Vol. 10, No. 1. (Jan., 1992), pp. 1-9. [Cited by 93] (6.82/year)
Conclusion: "This article developed two new specification tests for panel-data models. The first is a test to determine whether a panel-data model with individual-specific effects can be estimated using conventional estimators that assume that all instruments are strictly exogenous. The second is a test for the presence of individual fixed effects that is valid even when instruments are predetermined but not strictly exogenous. It also developed a new estimator that may yield more efficient estimates for panel-data models when instruments are predetermined but not strictly exogenous. Our empirical example demonstrated the importance of this work for determining the validity of the permanent-income hypothesis."
- BOUDOUKH, Jacob, Matthew P. RICHARDSON and Robert F. WHITELAW, 1994. A Tale of Three Schools: Insights on Autocorrelations of Short-Horizon Stock Returns, The Review of Financial Studies, Vol. 7, No. 3. (Autumn, 1994), pp. 539-573. [Cited by 80] (6.79/year)
Abstract: "This paper reexamines the autocorrelation patterns of short- horizon stock returns. We document empirical results which imply that these autocorrelations have been overstated in the existing literature. Based on several new insights, we provide support for a market efficiency-based explanation of the evidence. Our analysis suggests institutional factors are the most likely source of the autocorrelation patterns."
- CANINA, L., et al., 1998. Caveat Compounder: A Warning about Using the Daily CRSP Equal-Weighted Index to Compute Long-Run Excess Returns, The Journal of Finance, 53, 403-416. [Cited by 53] (6.77/year)
- GOODHART, C., T. ITO and R. PAYNE, 1995. One Day in June, 1993: A Study of the Working of Reuters 2000-2 Electronic Foreign Exchange Trading system. NBER Working Paper. [Cited by 70] (6.47/year)
- MCQUEEN, G., M. PINEGAR and S. THORLEY, 1996. Delayed Reaction to Good News and the Cross-Autocorrelation of Portfolio Returns. The Journal of Finance. [Cited by 62] (6.43/year)
Abstract: "We document a directional asymmetry in the small stock concurrent and lagged response to large stock movements. When returns on large stocks are negative, the concurrent beta for small stocks is high, but the lagged beta is insignificant. When returns on large stocks are positive, small stocks have small concurrent betas and very significant lagged betas. That is, the cross-autocorrelation puzzle documented by Lo and MacKinlay (199Oa) is associated with a slow response by some small stocks to good, but not to bad, common news. Time series portfolio tests and cross-sectional tests of the delay for individual securities suggest that existing explanations of the cross-autocorrelation puzzle based on data mismeasurement, minor market imperfections, or time-varying risk premiums fail to capture the directional asymmetry in the data."
- BIANCO, Simone and Roberto RENÒ, 2006. Dynamics of intraday serial correlation in the Italian futures market. Journal of Futures Markets, Volume 26, Issue 1, Pages 61-84, January 2006. [Cited by 1] (6.38/year)
Abstract: "The serial correlation of high-frequency intraday returns on the Italian stock index futures (FIB30) in the period 2000-2002 is studied. It is found that intraday autocorrelation is mostly negative for time scales lower than 20 minutes, mainly due to the bid-ask bounce effect. Although this supports the efficiency of the Italian futures market, evidence that intraday serial correlation becomes positive in high-volatility regimes is also provided. Moreover, it is found that it is mainly unexpected volatility that makes serial correlation rise, and not its predictable part. The results are supportive of the K. Chan (1993) model."
"The Efficient Market Hypothesis in its weakest form implies that asset returns should be serially uncorrelated, but there is pervasive evidence of serial autocorrelation in stock index returns (Lo and MacKinlay, 1988; Poterba and Summers, 1988) and stock portfolios (Conrad and Kaul, 1988; Mech, 1993), mixed evidence on stocks (Lo and MacKinlay, 1990b; Conrad and Kaul, 1989; Kim et al., 1991) and international assets (Patro and Wu, 2004), mainly depending on volumes and size (Llorente et al., 2002), while stock index futures display no autocorrelation, see Ahn et al. (2002) and Pan et al. (1997) for currency futures."
Bianco and Renò (2006)
- CONT, R., M. POTTERS and J.P. BOUCHAUD, 1997. Scaling in stock market data: stable laws and beyond. Scale invariance and beyond. [Cited by 56] (6.35/year)
- CONRAD, J. and G. KAUL, 1988. Time-Variation in Expected Returns, The Journal of Business, Vol. 61, No. 4. (Oct., 1988), pp. 409-425. [Cited by 108] (6.06/year)
Abstract: "This article characterizes the stochastic behavior of expected returns on common stock. We assume market efficiency and postulate an autoregressive process for conditional expected returns. We use weekly returns of 10 size-based portfolios over the 1962-85 period and find that (1) the variation through time in expected returns is well characterized by a stationary first-order autoregressive process: (2) the extracted expected returns explain a substantial proportion (up to 26%) of the variance in realized returns, and the magnitude of this proportion has a monotonic (inverse) relation with size; (3) the degree of variation in expected returns also changes systematically over time; and (4) the forecasts subsume the information in other potential predictor variables."
- VOGELSANG, T.J., 1998. Trend Function Hypothesis Testing in the Presence of Serial Correlation. Econometrica. [Cited by 45] (5.89/year)
Abstract: "Test statistics are proposed for testing hypotheses about the parameters of the deterministic trend function of a univariate time series. The tests are valid for general forms of serial correlation in the errors and do not require estimates (parametric or nonparametric) of serial correlation parameters. The tests are valid for stationary and unit root errors. Allowable trend functions include linear polynomials of time that may have structural change. Asymptotic results are applied to a model with a simple linear trend and are used to construct confidence intervals for average GNP growth rates for eight industrialized countries using postwar data."
- BALL, Ray and S. P. KOTHARI, 1989. Nonstationary expected returns: Implications for tests of market efficiency and serial correlation in returns, Journal of Financial Economics, Volume 25, Issue 1, November 1989, Pages 51-74. [Cited by 97] (5.83/year)
Abstract: "Recent evidence reveals significant negative serial correlation in aggregate (market-wide) stock returns. We extend this result to relative (market-adjusted) returns, demonstrating negative serial correlation in five-year returns. We then test two competing explanations: (1) market mispricing and (2) changing expected returns in an efficient market. The tests are conducted using the capital asset pricing model to estimate relative returns. The evidence suggests that negative serial correlation in relative returns is due almost entirely to variation in relative risks, and therefore expected relative returns, through time. We document substantial relative risk shifts, particularly for extreme-performing stocks."
- MECH, T.S., 1993. Portfolio return autocorrelation. Journal of Financial Economics, Volume 34, Issue 3 , December 1993, Pages 307-344. [Cited by 73] (5.70/year)
Abstract: "This paper investigates whether portfolio return autocorrelation can be explained by time-varying expected returns, nontrading, state limit orders, market maker inventory policy, or transaction costs. Evidence is consistent with the hypothesis that transaction costs cause portfolio autocorrelation by slowing price adjustment. I develop a transaction-cost model which predicts that prices adjust faster when changes in valuation are large in relation to the bid-ask spread. Cross-sectional tests support this prediction, but time-series tests do not."
- AHN, Dong-Hyun, et al., 2002. Partial Adjustment or Stale Prices? Implications from Stock Index and Futures Return Autocorrelations, The Review of Financial Studies, Vol. 15, No. 2, Special Issue: Conference on Market Frictions and Behavioral Finance. (2002), pp. 655-689. [Cited by 21] (5.51/year)
Abstract: "We investigate the relation between returns on stock indices and their corresponding futures contracts to evaluate potential explanations for the pervasive yet anomalous evidence of positive, short-horizon portfolio autocorrelations. Using a simple theoretical framework, we generate empirical implications for both microstructure and partial adjustment models. The major findings are (i) return autocorrelations of indices are generally positive even though futures contracts have autocorrelations close to zero, and (ii) these autocorrelation differences are maintained under conditions favorable for spot-futures arbitrage and are most prevalent during low-volume periods. These results point toward microstructure-based explanations and away from explanations based on behavioral models."
- LEBARON, Blake, 1992. Some Relations Between Volatility and Serial Correlations in Stock Market Returns, The Journal of Business, Vol. 65, No. 2 (Apr., 1992) , pp. 199-219. [Cited by 66] (4.78/year)
Abstract: "This article explores the relation between serial correlation and volatility for several different stock return series at daily and weekly frequencies. It is found that serial correlations are changing over time and are related to stock return volatility. An extension to the GARCH model is proposed and estimated, revealing parameters consistent with other findings in this article."
- CAMPBELL, J.Y.Y., et al., 2001. Stock Market Mean Reversion and the Optimal Equity Allocation of a Long-Lived Investor, European Finance Review, Issue: Volume 5, Number 3, Date: January 2001, Pages: 269 - 292. [Cited by 22] (4.57/year)
Abstract: "This paper solves numerically the intertemporalconsumption and portfolio choiceproblem of an infinitely-lived investor whofaces a time-varying equity premium.The solutions we obtain are very similarto the approximate analytical solutionsof Campbell and Viceira (1999), except atthe upper extreme of the state spacewhere both the numerical consumption andportfolio rules flatten out.We also consider a constrained version ofthe problem in which the investor facesborrowing and short-sales restrictions.These constraints bind when the equitypremium moves away from its mean in eitherdirection, and are particularly severe forrisk-tolerant investors. The constraints havesubstantial effects on optimalconsumption, but much more modest effects onoptimal portfolio choice in theregion of the state space where they are notbinding."
- RICHARDSON, M., 1993. Temporary Components of Stock Prices: A Skeptic's View. Journal of Business & Economic Statistics. [Cited by 57] (4.45/year)
Abstract: "Recent empirical work has uncovered U-shaped patterns of large magnitude in the serial-correlation estimates of multiyear stock returns. The current literature in finance has taken this evidence to mean that there exists a temporary component of stock prices. This article provides an alternative explanation regarding these findings. Specifically, we show that the patterns in serial-correlation estimates and their magnitude observed in previous studies should be expected under the null hypothesis of serial independence."
- LEBARON, B., 1992. Some Relations Between Volatility and Serial Correlations in Stock Market Returns. The Journal of Business. [Cited by 57] (4.18/year)
Abstract: "This article explores the relation between serial correlation and volatility for several different stock return series at daily and weekly frequencies. It is found that serial correlations are changing over time and are related to stock return volatility. An extension to the GARCH model is proposed and estimated, revealing parameters consistent with other findings in this article."
- SENTANA, E. and S. WADHWANI, 1992. Feedback Traders and Stock Return Autocorrelations: Evidence from a Century of Daily Data. The Economic Journal. [Cited by 56] (4.11/year)
Abstract: "The authors investigate whether the degree of autocorrelation shown by high frequency stock returns changes with volatility. This may result from nontrading effects, feedback trading strategies, or variable risk aversion. The authors' results indicate that when volatility is low, daily (and hourly) stock returns exhibit positive autocorrelation, but when it is high, returns exhibit negative serial correlation. They also find an important asymmetry--negative serial correlation is more likely after price declines. This is consistent with price declines being more likely to induce positive feedback trading. The authors also find no significant relation between margin requirements and the autocorrelation of returns."
- LYONS, R.K., 1995. Foreign Exchange Volume: Sound and Fury Signifying Nothing?. NBER WORKING PAPER SERIES. [Cited by 44] (4.06/year)
- RONN, E., 1998. The impact of large changes in asset prices on intra-market correlations in the stock and bond …. Manuscript, Department of Finance, University of Texas, …. [Cited by 29] (3.84/year)
- HONG, Y., 1996. Consistent Testing for Serial Correlation of Unknown Form. Econometrica. [Cited by 37] (3.84/year)
Abstract: "This paper proposes three classes of consistent tests for serial correlation of the residuals from a linear dynamic regression model. The tests are obtained by comparing a kernel-based spectral density estimator and the null spectral density using three divergence measures. The null normal distributions are invariant whether the regressors include lagged dependent variables. Both asymptotic local and global power properties are investigated. G. Box and D. Pierce's (1970) test can be viewed as a test based on the truncated kernel; many other kernels deliver better power than Box and Pierce's test. A simulation study shows that the new tests have good power against weak and strong dependence."
- CHAN, K., 1993. Imperfect Information and Cross-Autocorrelation Among Stock Prices, The Journal of Finance. [Cited by 48] (3.80/year)
Abstract: "The author develops a model to explain why stock returns are positively cross-autocorrelated. When marketmakers observe noisy signals about the value of their stocks but cannot instantaneously condition prices on the signals of other stocks, which contain marketwide information, the pricing error of one stock is correlated with the other signals. As marketmakers adjust prices after observing true values or previous price changes of other stocks, stock returns become positively cross-autocorrelated. If the signal quality differs among stocks, the cross-autocorrelation pattern is asymmetric. The author shows that both own- and cross-autocorrelations are higher when market movements are larger."
- GOODHART, C.A.E. and L. FIGLIUOLI, 1991. Every Minute Counts in Financial Markets, Journal of International Money and Finance 10, 23-52. [Cited by 65] (3.65/year)
Abstract: "This paper represents an introductory study of ultra high frequency, minuute-by-minute data, for forex spot rates (bid-ask Reuters quotes) on three days, Autumn 1987. The frequency of price revision, size of spread, and statistical characteristics are measured. The series exhibit (time varying) leptokurtosis, unit roots, and first-order negative correlation, the latter especially in disturbed ‘jumpy’ markets. The effect of time aggregation on these characteristics is examined, and variance ratios are analyzed. Multivariate analysis revealed significant relationships between lagged exchange rates, both the own rate and the key deutsche mark/US dollar rate, and the current spot rate."
- DURBIN, J. and G.S. WATSON, 1971. Testing for Serial Correlation in Least Squares Regression. III. Biometrika. [Cited by 121] (3.49/year)
Abstract: "The construction of tests of model specification is considered from a general point of view. The results are applied to testing the serial independence of the disturbances in a regression model where some of the regressors are lagged dependent variables. It is shown that the asymptotic distribution of the lag-1 serial correlation coefficient calculated from the least-squares residuals differs from that of the coefficient calculated from the true disturbances. A consequence of this is that tests of serial independence based on the residuals from regression on fixed regressors are invalid when applied to models containing lagged dependent variables even when the null hypothesis of serial independence is true. Tests which are asymptotically valid for the large-sample case are suggested."
- HOLDEN, C.W. and A. SUBRAHMANYAM, 2001. News Events, Information Acquisition, and Serial Correlation. The Journal of Business. [Cited by 16] (3.45/year)
Abstract: "We develop a model that accounts for medium-term continuation (momentum) in asset returns by analyzing information acquisition about news events (such as earnings announcements) in a multiperiod setting. As more and more agents become informed about news events, temporal uncertainty is resolved endogenously through market prices over time, which leads to positive autocorrelations in asset returns. We empirically estimate serial correlations over medium-term horizons for portfolios sorted by firm size and past stock performance and find that calibration of serial correlations in our model spans the range of empirically estimated correlations."
- PASQUINI, Michele and Maurizio SERVA, 1998. Multiscale behaviour of volatility autocorrelations in a financial market. Arxiv preprint cond-mat/9810232. [Cited by 25] (3.27/year)
Abstract: "We perform a scaling analysis on NYSE daily returns. We show that volatility correlations are power-laws on a time range from one day to one year and, more important, that they exhibit a multiscale behaviour."
- CIZEAU, P., M. POTTERS and J.P. BOUCHAUD, 2001. Correlation structure of extreme stock returns. Arxiv preprint cond-mat/0006034. [Cited by 14] (3.07/year)
"It is commonly believed that the correlations between stock returns increase in high volatility periods. We investigate how much of these correlations can be explained within a simple non-Gaussian one-factor description with time independent correlations. Using surrogate data with the true market return as the dominant factor, we show that most of these correlations, measured by a variety of different indicators, can be accounted for."
- ATCHISON, M.D., K.C. BUTLER and R.R. SIMONDS, 1987. Nonsynchronous Security Trading and Market Index Autocorrelation. The Journal of Finance, Vol. 42, No. 1 (Mar., 1987), pp. 111-118. [Cited by 57] (3.03/year)
Abstract: "The theoretical portfolio autocorrelation due solely to nonsynchronous trading is estimated from a derived model. This estimated level is found to be substantially less than that observed empirically. The theoretical and empirical relationship between portfolio size and autocorrelation also is investigated. The results of this study suggest that other price-adjustment delay factors in addition to nonsynchronous trading cause the high autocorrelations present in daily returns on stock index portfolios."
- JEGADEESH, N. and S. TITMAN, 1995. Short-horizon return reversals and the bid-ask spread, Journal of Financial Intermediation, 4, 116-132. [Cited by 32] (2.96/year)
- NEELY, C.J. and P. WELLER, 1999. Intraday Technical Trading in the Foreign Exchange Market. research.stlouisfed.org. [Cited by 20] (2.94/year)
A number of authors have found negative first-order autocorrelation in exchange rate returns at various high-frequency horizons and some have offered explanations. Baillie and Bollerslev (1991) claim that nonsynchronous trading is responsible for the negative autocorrelation in hourly data. This explanation is implausible for our data set. For example, the nonsynchronous trading model of Lo and Mackinlay (1990) implies negative autocorrelation several orders of magnitude smaller than that actually observed. Zhou (1996) suggests that negative autocorrelation in tick-by-tick data is a consequence of “errors in data” and “screen fighting.” Again, we find neither explanation convincing in our (lower-frequency) half-hourly data. Screen fighting effects are unlikely to persist for so long. Another potential explanation is provided by Danielsson and Payne (2001), who document differences between indicative quotes of the type used here and firm interdealer quotes at very high frequencies. These differences disappear, however, as one samples returns at five- (or more) minute intervals. Therefore, it appears to be an unlikely explanation for autocorrelation in 30-minute returns7.
Neely and Weller (2003)
- LOUGHRAN, Tim and Jay R. RITTER, 1996. Long-Term Market Overreaction: The Effect of Low-Priced Stocks. The Journal of Finance, Vol. 51, No. 5 (Dec., 1996), pp. 1959-1970. [Cited by 28] (2.85/year)
Abstract: "Conrad and Kaul (1993) report that most of De Bondt and Thaler's (1985) long-term overreaction findings can be attributed to a combination of bid-ask effects when monthly cumulative average returns (CARs) are used, and price, rather than prior returns. In direct tests, we find little difference in test-period returns whether CARs or buy-and-hold returns are used, and that price has little predictive ability in cross-sectional regressions. The difference in findings between this study and Conrad and Kaul's is primarily due to their statistical methodology. They confound cross-sectional patterns and aggregate time-series mean reversion, and introduce a survivor bias. Their procedures increase the influence of price at the expense of prior returns."
- ATCHISON, M.D., K.C. BUTLER and R.R. SIMONDS, 1987. Nonsynchronous Security Trading and Market Index Autocorrelation. The Journal of Finance. [Cited by 50] (2.68/year)
Abstract: "This paper investiga tes the extent to which nonsynchronous security trading explains observed autocorrelations in daily returns on stock market indices. The theoretical portfolio autocorrelation due solely to nonsynchronous trading is estimated from a derived model. This estimated level is found to be substantially less than that observed empirically. The theoretical and empirical relationship between portfolio size and autocorrelation is also investigated. The results of this study suggest that other price-adjustment delay factors, in addition to nonsynchronous trading, cause the high autocorrelations present in daily returns on stock index portfolios."
- CONRAD, J. and G. KAUL, 1989. Mean reversion in short-horizon expected returns, The Review of Financial Studies, Vol. 2, No. 2. (1989), pp. 225-240. [Cited by 45] (2.65/year)
Abstract: "This article develops and estimates a simple model for monthly expected stock returns that relies on the rapidly decaying structure of shorter-horizon (weekly) expected returns. The most striking aspect of our findings is that the rapid mean reversion in short-horizon expected returns implies much greater variation through time in monthly expected returns than has been documented in earlier studies. For instance, during the 1962 to 1985 period, over 25 percent of the return variance of small firms can be explained by time variation in expected returns."
- FISHER, L., 1966. Some New Stock-Market Indexes, The Journal of Business, 29, 191-225. [Cited by 100] (2.51/year)
- SHEN, C.H. and L.R. WANG, 1998. Daily serial correlation, trading volume and price limits: Evidence from the Taiwan stock market. Pacific-Basin Finance Journal, Volume 6, Number 3, August 1998, pp. 251-273(23) [Cited by 19] (2.43/year)
Abstract: "The relationship among daily stock return autocorrelation, trading volume, and price limits are investigated in this paper. Twenty-four Taiwan individual stocks are adopted here. We found that increasing the volume reduces the daily autocorrelation for nearly half of the stocks. This negative volume effect is contrary to the positive price-limit effect, which strengthens the autocorrelation. We use OLS, generalized autoregressive conditional heteroscedasticity (GARCH) and generalized method of moment (GMM) to investigate the sensitivity of the estimation results. Our results display robustness across estimation methods."
- MORIKAWA, T., 1994. Correcting state dependence and serial correlation in the RP/SP combined estimation method. Transportation. [Cited by 28] (2.41/year)
Abstract: "Revealed preference (RP) data and stated preference (SP) data have complementary characteristics for model estimation. To enhance the advantages of both data types, a combined estimation method is proposed. This paper discusses the method and practical considerations in applying it, and introduces a new method of considering serial correlation of RP and SP data. An empirical analysis is also presented."
- SAFVENBLAD, P., 2000. Trading Volume and Autocorrelation: Empirical Evidence from the Stockholm Stock Exchange, Journal of Banking and Finance. [Cited by 13] (2.31/year)
Abstract: "This paper provides an extensive empirical investigation into the sources of index return autocorrelation, focusing on the relation between autocorrelation in individual stock returns and autocorrelation in index returns. The study uses daily data from the Stockholm Stock Exchange over the period 1980-1995 and reports three main empirical findings. Daily Swedish stock index returns exhibit strong, and consistently positive, first order autocorrelation throughout the sample period. Positive autocorrelation is observed for return frequencies between 1 day and 3 months. The most liquid stocks exhibit strong positive return autocorrelation. Less liquid stocks exhibit weak or negative return autocorrelation. Autocorrelation is asymmetric, high after days of above average performance of the stock market, low after days of below average performance. When compared to the other days of the week, both index returns and individual stock returns exhibit the strongest autocorrelation following on Friday returns. The transaction cost hypothesis was tested using the Swedish stock market transaction tax. Results indicate lower precision of stock prices during the transaction tax period, but no direct effect on return autocorrelation. The paper concludes that at least three sources contribute to observed return autocorrelation. For daily and short-term returns, profit taking and nonsynchronous trading are the probable causes of observed autocorrelation. For monthly and longer term returns, time-varying expected returns best describe the empirical results."
- RICHARDSON, M. and T. SMITH, 1994. A Unified Approach to Testing for Serial Correlation in Stock Returns. The Journal of Business. [Cited by 25] (2.15/year)
- PONIEWIERSKI, A., et al., 1999. … -Peierls fluctuations: Scaling form of the dynamic density autocorrelation function for smectic-A …. PHYSICAL REVIEW-SERIES E-. [Cited by 14] (2.11/year)
- GOODHART, C.A.E., 1991. 'News' and the Foreign Exchange Market. Manchester Statistical Society. [Cited by 31] (2.09/year)
- HASBROUCK, J. and T.S.Y. HO, 1987. Order Arrival, Quote Behavior, and the Return-Generating Process, The Journal of Finance, 42, 1035-1048. [Cited by 39] (2.07/year)
- WORKING, H., 1960. Note on the Correlation of First Differences of Averages in a Random Chain. Econometrica. [Cited by 94] (2.06/year)
- KOUTMOS, G., 1997. Feedback trading and the autocorrelation pattern of stock returns: further empirical evidence. JOURNAL OF INTERNATIONAL MONEY AND FINANCE. [Cited by 17] (1.97/year)
- SHEN, C.H. and L.R. WANG, 1998. Daily Serial Correlation, Trading Volume, and Price Limits: Evidence from the Taiwan Stock Market. Pacific-Basin Finance Journal. [Cited by 15] (1.96/year)
- CHANG, E.C., G.R. MCQUEEN and J.M. PINEGAR, 1999. Cross-autocorrelation in Asian stock markets. PACIFIC BASIN FINANCE JOURNAL. [Cited by 13] (1.96/year)
- POTZELBERGER, K. and L. SOGNER, 2003. Sample Autocorrelation Learning in a Capital Market Model. Journal of Economic Behavior and Organization. forthcoming. [Cited by 5] (1.90/year)
- CONRAD, J., G. KAUL and M. NIMALENDRAN, 1991. Components of Short-horizon Individual Security Returns, Journal of Financial Economics, 29, 365-384. [Cited by 27] (1.82/year)
- BLANCIFORTI, L. and R. GREEN, 1983. An Almost Ideal Demand System Incorporating Habits: An Analysis of Expenditures on Food and …. The Review of Economics and Statistics. [Cited by 40] (1.77/year)
- GONG, P., 1999. Optimal Harvest Policy with First-Order Autoregressive Price Process. JOURNAL OF FOREST ECONOMICS. [Cited by 11] (1.66/year)
- PATRO, D.K. and Y. WU, 2004. Predictability of short-horizon returns in international equity markets, Journal of Empirical Finance, Volume 11, Issue 4 , September 2004, Pages 553-584. [Cited by 3] (1.65/year)
Abstract: "This paper examines the predictability of equity index returns for 18 developed countries. Based on the variance ratio test, the random walk hypothesis can be rejected at conventional significance levels for 11 countries with daily data and for 15 countries with weekly data. Monthly indices may well be characterized as a random walk for the majority of countries. The excess returns from buying past winners and selling past losers are positive and particularly striking for daily data, where they are not only statistically significant but also economically important in the absence of transaction costs. Imposing a reasonable transaction cost substantially reduces the profitability."
- APARICIO, F.M. and A. ESCRIBANO, 1998. Information-theoretic analysis of serial dependence and cointegration. Studies in Nonlinear Dynamics and Econometrics. [Cited by 12] (1.59/year)
- CARR, P. and R. LEE, 2003. Trading autocorrelation. Unpublished paper: Courant Institute, NYU. [Cited by 4] (1.52/year)
- FLOOD, M.D., 1994. Market structure and inefficiency in the foreign exchange market, Journal of International Money and Finance, 13, 131-158. [Cited by 22] (1.39/year)
- CHEN, J. and H. HONG, 2002. Discussion of" Momentum and Autocorrelation in Stock Returns". REVIEW OF FINANCIAL STUDIES. [Cited by 5] (1.38/year)
- PAN, M.S., K.C. CHAN and F.R. CW, 1997. Do currency futures prices follow random walks?. Journal of Empirical Finance, Volume 4, Issue 1 , January 1997, Pages 1-15. [Cited by 12] (1.36/year)
Abstract: "This paper examines the random walk process for four currency futures prices for the period 1977–1987 by using the variance ratio test. The random walk hypothesis is tested through asymptotic standardized statistics as well as by computing the significance level based on the bootstrap method. Both long time-series prices and individual contract prices for four currency futures, the British pound, the German mark, the Japanese yen, and the Swiss franc are analyzed. The results provide little evidence against the random walk null hypothesis, though non-randomness is documented in the Japanese yen. Additionally, the currency futures markets apparently become more efficient as markets mature over time."
- CHEN, Joseph and Harrison HONG, 2002. Discussion of ‘Momentum and Autocorrelation in Stock Returns'. Review of Financial Studies, Vol. 15, No. 2, Special Issue: Conference on Market Frictions and Behavioral Finance (2002) , pp. 565-573. [Cited by 5] (1.31/year)
"Goodhart and Figliuoli (1991) examine minute-by-minute foreign exchange rates as they are reported in Reuters’ FXFX page and they find clear evidence of negative first-order autocorrelation, especially after jumps in the exchange rate level, for up to 4 minutes.34 This evidence is corroborated by Bollerslev and Domowitz (1993) who also report evidence of negative serial correlation in the returns series calculated from either bid or ask quotes. This negative first-order autocorrelation is also confirmed by Baillie and Bollerslev (1990) using the same data set as Goodhart and Figliuoli (1991) and by Zhou (1992) using a different data set. Low and Muthuswamy (1996) also conclude that 5-minute returns of the USD/JPY, USD/DEM and DEM/JPY exchange rates exhibit significant serial dependencies (i.e. heteroskedastic), possibly nonlinear in nature.
A possible explanation for this observation could be that market participants with diverging opinions revise their views upon the arrival of new information. Other researchers attribute this evidence to the fact that FXFX quote prices are indicative and quotes tend to move depending on the banks’ order imbalances, or persistent tendencies of banks to quote high or low, as in Bollerslev and Domowitz (1993), or pure noise, as in Zhou (1992 [?]), while Goodhart and Payne (1995) attribute it to the presence of thin markets."
Dunis and Zhou (1998) page 10
"We then demonstrate that as indicated by the Hurst exponent, USD/DEM tick data are slightly trending, not mean-reverting, on time scales of 60 ticks (about 15 minutes) or less. This empirical result agrees with that obtained by Müller et al. (1990) using the drift exponent for data sampled in θ-time (a deseasonalized physical time scale) on time scales of 10 minutes or more."
Dunis and Zhou (1998) page 30
"...short-term negative autocorrelations, rather than to intrinsic dependencies in the price movements, and the underlying behavior of the series on longer time scales is actually trending on average. Our empirical result that long-term trends are present in FX data is consistent with results obtained by Müller et al. (1990) using the drift exponent on time scales of 10 minutes or more."
Dunis and Zhou (1998) page 33
"Analysis of autocorrelations of price variations with a frequency of 20 minutes indicates an absence of memory (Guillaume et al. 1994). Furthermore, the analysis of absolute price variations generates richer information and exhibits considerable seasonality (physical time) which is scarcely reduced by the use of theta time. This last representation shows an autocorrelation function that decreases hyperbolically and non-exponentially, indicating an extensive and substantial memory in the series."
Dunis and Zhou (1998) page 284-285
- DUNIS, C. and B. ZHOU, 1998. Nonlinear modelling of high frequency financial time series. Wiley New York. [Cited by 10] (1.28/year)
- EOM, K.S., S.B. HAHN and S. JOO, 2004. Partial price adjustment and autocorrelation in foreign exchange markets. Preprint, University of California at Berkeley. [Cited by 2] (1.22/year)
"However, some recent research has sharply contradicted these ndings. Using a statistical comparison of variances across different investment horizons applied to the weekly returns of a portfolio of stocks from 1962 to 1985, Lo and MacKinlay (1988) nd that the random walk hypothesis can be rejected with great statistical confidence (well in excess of 0.999). In fact, the weekly returns of a portfolio containing an equal dollar amount invested in each security traded on the New York and American Stock Exchanges (called an equal-weighted portfolio) exhibit a striking relation from one week to the next: a first-order autocorrelation coeficient of 0.30.
An autocorrelation of 0.30 implies that approximately 9% of the variability of next week's return is explained by this week's return. An equally weighted portfolio containing only the stocks of “smaller” companies, companies with market capitalization in the lowest quintile, has a autocorrelation coeffcient of 0.42 during the 1962 to 1985 sample period, implying that about 18% of the variability in next week's return can be explained by this week's return. Although numbers such as 9% and 18% may seem small, it should be kept in mind that 100% predictability yields astronomically large investment returns; a very tiny fraction of such returns can still be economically meaningful.
These findings surprise many economists because a violation of the random walk necessarily implies that price changes are forecastable to some degree. But since forecasts of price changes are also subject to random fluctuations, riskless profit opportunities are not an immediate consequence of forecastability. Nevertheless, economists still cannot completely explain why weekly returns are not a “fair game”. Two other empirical facts add to this puzzle: (1) Weekly portfolio returns are strongly positively autocorrelated, but the returns to individual securities generally are not; in fact, the average autocorrelation|averaged across individual securities|is negative (and statistically insignificant); (2) The predictability of returns is quite sensitive to the holding period: serial dependence is strong and positive for daily and weekly returns, but is virtually zero for returns over a month, a quarter, or a year.
For holding periods much longer than one week, e.g., three to five years, Fama and French (1988) and Poterba and Summers (1988) find negative serial correlation in US stock returns indexes using data from 1926 to 1986. Although their estimates of serial correlation coefficients seem large in magnitude, there is insufficient data to reject the random walk hypothesis at the usual levels of significance. Moreover, a number of statistical biases documented by Kim, Nelson, and Startz (1991) and Richardson (1993) cast serious doubt on the reliability of these longer-horizon inferences."
Lo (2000)
- LO, A.W., 2000. Finance: A Selective Survey.. Journal of the American Statistical Association. [Cited by 7] (1.20/year)
- BHARGAVA, R., A. BOSE and D.A. DUBOFSKY, 1998. Exploiting International Stock Market Correlations with Open-end International Mutual Funds. Journal of Business Finance & Accounting. [Cited by 9] (1.19/year)
- BALLOCCHI, G., et al., 1999. Intraday Statistical Properties of Eurofutures, Derivatives Quarterly, 6, 28-44. [Cited by 8] (1.17/year)
- HAKANSSON, N.H., 1971. On Optimal Myopic Portfolio Policies, with and Without Serial Correlation of Yields. The Journal of Business. [Cited by 40] (1.15/year)
- MCKENZIE, M.D. and R.W. FAFF, 2003. The Determinants of Conditional Autocorrelation in Stock Returns. Journal of Financial Research. [Cited by 3] (1.14/year)
- MCKENZIE, M.D. and R.W. FAFF, 2003. The Determinants of Conditional Autocorrelation in Stock Returns. Journal of Financial Research. [Cited by 3] (1.07/year)
Abstract: "We investigate whether return volatility, trading volume, return asymmetry, business cycles, and day-of-the-week are potential determinants of conditional autocorrelation in stock returns. Our primary focus is on the role of feedback trading and the interplay of return volatility. We present empirical evidence using conditional autocorrelation estimates generated from multivariate generalized autoregressive conditional heteroskedasticity (M-GARCH) models for individual U.S. stock and index data. In addition to return volatility, we find that trading volume and market returns are important in explaining the time-varying patterns of return autocorrelation."
- ATEN, B., 1996. Evidence of Spatial Autocorrelation in International Prices. Review of Income and Wealth. [Cited by 10] (1.04/year)
"There has also been extensive recent work on the temporal dynamics of security returns. For instance, Lo and MacKinlay (1988) find that weekly returns on portfolios of NYSE stocks grouped according to size show positive autocorrelation. Conrad and Kaul (1988) examine the autocorrelations of Wednesday-to-Wednesday returns (to mitigate the nonsynchronous trading problem) for size-grouped portfolios of stocks that trade on both Wednesdays. Similar to the findings of Lo and MacKinlay (1988), they find that weekly returns are positively autocorrelated. Cutler, Poterba, and Summers (1991) present results from many different asset markets generally supporting the hypothesis that returns are positively correlated at the horizon of several months, and negatively correlated at the 3–5 year horizon. Lo and MacKinlay (1990) report positive serial correlation in weekly returns for indices and portfolios, and negative serial correlation for individual stocks. Chopra, Lakonishok, and Ritter (1992), De Bondt and Thaler (1985), Fama and French (1986), and Poterba and Summers (1988) find negative serial correlation in returns of individual stocks and various portfolios over three- to ten-year intervals. Jegadeesh (1990) finds negative serial correlation for lags up to two months, and positive correlation for longer lags. Lehmann (1990) and French and Roll (1986) report negative serial correlation at the level of individual securities for weekly and daily returns. Overall, the findings of recent literature confirm the findings of earlier literature that the daily and weekly returns are predictable from past returns and other economic and financial variables."
Gençay and Stengos (1997)
- GENCAY, R. and T. STENGOS, 1997. Technical Trading Rules and the Size of the Risk Premium in Security Returns. Studies in Nonlinear Dynamics and Econometrics. [Cited by 9] (1.02/year)
- GOODHART, C. and R. PAYNE, 1996. Microstructural Dynamics in a Foreign Exchange Electronic Broking System, Journal of International Money and Finance [Cited by 10] (1.02/year)
Abstract: "This paper explores the relationships between quotations, spreads and transactions in the Foreign Exchange market. Such interactions have been the subject of much work in markets such as the NYSE, but until now have gone unexamined in the FX market owing to a lack of data. Using a 7 hour, transactions-based data set we examine the determinants of both quote revisions and spreads. The results indicate that trades are a major factor in spread determination and quote revisions. Furthermore, there is evidence that the widely documented negative auto-correlation in quote returns is at least partially caused by the ‘thinness’ of this particular segment of the FX market."
- RENDLEMAN, R.J., C.P. JONES and H.A. LATANE, 1987. FURTHER INSIGHT INTO THE STANDARDIZED UNEXPECTED EARNINGS ANOMALY: SIZE AND SERIAL CORRELATION …. The Financial Review. [Cited by 18] (0.97/year)
- WASER, N.M. and R.J. MITCHELL, 1990. Nectar Standing Crops in Delphinium Nelsonii Flowers: Spatial Autocorrelation among Plants?. Ecology. [Cited by 15] (0.96/year)
- … MS GILL, L GILL, AJ WHATMORE, GM ADDISON, DA PRICE …, 1996. Infradian rhythms in urinary growth hormone excretion. J Clin Endocrinol Metab. [Cited by 9] (0.93/year)
- BLANDON, J.G., 2002. New findings regarding return autocorrelation anomalies and the importance of non-trading periods. Unpublished Manuscript. Department of Economics and Business …. [Cited by 3] (0.83/year)
- DURBIN, J., 1969. Tests for Serial Correlation in Regression Analysis Based on the Periodogram of Least-Squares …. Biometrika. [Cited by 28] (0.76/year)
- MCINISH, T.H. and R.A. WOOD, 1991. Autocorrelation of Daily Index Returns: Intraday-to-Intraday versus Close-to-Close Intervals. Journal of Banking and Finance 15, 193-206. [Cited by 11] (0.74/year)
- COHEN, K., S. MAIER and R. SCHWARTZ, 1979. D. Whitcomb, 1979,“On the Existence of Serial Correlation in an Efficient Securities Market”. TIMS Studies in the Management Sciences. [Cited by 19] (0.71/year)
- LOW, A. and J. MUTHUSWAMY, 1996. Information flows in high frequency exchange rates. Forecasting Financial Markets: Exchange Rates, Interest …. [Cited by 7] (0.71/year)
- KUO, C.L., 1996. Serial correlation and seasonality in the real estate market. The Journal of Real Estate Finance and Economics. [Cited by 6] (0.62/year)
- PERRY, P.R., 1985. Portfolio Serial Correlation and Nonsynchronous Trading. The Journal of Financial and Quantitative Analysis. [Cited by 12] (0.58/year)
- OGDEN, J., 1997. Empirical Analyses of Three Explanations for the Positive Autocorrelation of Short-Horizon Stock …. Review of Quantitative Finance and Accounting. [Cited by 5] (0.58/year)
- GU, Anthony Yanxiang and Joseph FINNERTY, 2002. The Evolution of Market Efficiency: 103 Years Daily Data of the Dow. Review of Quantitative Finance and Accounting. [Cited by 2] (0.52/year)
Abstract: "Autocorrelation in daily returns of the Dow 30 Index fluctuates significantly over time and reveals a declining trend after World War II. The relation between autocorrelation and volatility is negative and nonlinear. The relation between autocorrelation and volume is also negative and nonlinear. Returns exhibit positive autocorrelation during years with higher autocorrelation, and negative autocorrelation during years with lower autocorrelation. Positive autocorrelation appears more frequently during periods of low volatility, while negative autocorrelation appears more frequently during periods of high volatility. Current period's autocorrelation is related to previous period's autocorrelation and to both the previous and the current period's volatility and rate of return, which implies that investors incorporate previous period's pattern of market behavior into their trading strategy."
- GHOSE, D. and K.F. KRONER, 1995. Temporal Aggregation of High Frequency Financial Data. Proceedings of the HFDF-I Conference. [Cited by 5] (0.46/year)
- AHN, D.H., et al., 1999. Behavioralize This! International Evidence on Autocorrelation Patterns of Stock Index and Futures …. [Cited by 3] (0.45/year)
[Hang Seng Index futures]
We compute both three- and five-minute autocorrelation results and find that they are similar. For the five-minute figures, we use one model to fit all three periods. The five-minute results show that the HSI spot index return has a relatively large autocorrelation (0.159) at the first lag and positive and significant autocorrelations up to the second lag. The HSI index futures series shows positive and significant autocorrelations only for the first lag, and its magnitude (0.062) is relatively small."
Jiang, Fung and Cheng (2001)
- JIANG, L., J.K.W. FUNG and L.T.W. CHENG, 2001. The Lead-Lag Relation Between Spot and Futures Markets Under Different Short-Selling Regimes. The Financial Review. [Cited by 2] (0.42/year)
Abstract: "We examine the lead-lag relation between index futures and the underlying index under three types of short-selling restrictions on stocks in Hong Kong. Our results indicate that lifting short-selling restrictions can enhance the informational efficiency of the stock market relative to the index futures. We also investigate the impact of two market characteristics, market conditions and the magnitude of mispricing on the lead-lag relations under different short-selling regimes. Our findings suggest that if we remove restrictions, the contemporaneous price relation between the futures and cash markets becomes stronger particularly in the falling market and when the cash market is relatively overpriced."
- WILTSHAW, D.G., 1996. Spatial autocorrelation and valuation accuracy: a neglected methodological problem. Journal of Property Research. [Cited by 4] (0.42/year)
- HAWAWINI, G.A., 1980. Intertemporal Cross-Dependence in Securities Daily Returns and the Short-Run Intervaling Effect on …. The Journal of Financial and Quantitative Analysis. [Cited by 9] (0.35/year)
- SCHWARTZ, Robert A. and David K. WHITCOMB, 1977. Evidence on the Presence and Causes of Serial Correlation in Market Model Residuals. The Journal of Financial and Quantitative Analysis, Vol. 12, No. 2 (Jun., 1977), pp. 291-313. [Cited by 10] (0.35/year)
- SCHWARTZ, R.A. and D.K. WHITCOMB, 1977. Evidence on the Presence and Causes of Serial Correlation in Market Model Residuals. The Journal of Financial and Quantitative Analysis. [Cited by 10] (0.35/year)
- MORGAN, G., P. SMITH and S. THOMAS, 2000. Portfolio Return Autocorrelation and Non-Synchronous Trading in UK Equities. Discussion Papers in Economics, No. [Cited by 2] (0.35/year)
- BERGLUND, T. and E. LILJEBLOM, 1988. Market Serial Correlation on a Small Security Market: A Note. The Journal of Finance. [Cited by 6] (0.34/year)
- GOODHART, C.E. and L. FIGLIUOLI, 1992. The Geographical Location of the Foreign Exchange Market: A Test of an'islands' Hypothesis. London School of Economics and Political Science, Financial …. [Cited by 6] (0.34/year)
- GOLDMAN, M.B. and A. BEJA, 1979. Market Prices vs. Equilibrium Prices: Returns' Variance, Serial Correlation, and the Role of the …. The Journal of Finance. [Cited by 8] (0.30/year)
- BOHL, M.T. and S. REITZ, 2002. … of Positive Feedback Trading on Return Autocorrelation: Evidence for the German Stock Market. Arbeitspapier Europa-Universität Viadrina. Frankfurt (Oder). [Cited by 1] (0.28/year)
- CONNOLLY, R. and C. STIVERS, 1998. Conditional Stock Market Return Autocorrelation and Price Formation: International Evidence from Six …. [Cited by 2] (0.26/year)
- CONNOLLY, R. and C. STIVERS, 1998. Conditional Stock Market Return Autocorrelation and Price Formation: International Evidence from Six …. [Cited by 2] (0.26/year)
- BOOTH, G.G., 1998. Interaction of volatility and autocorrelation in foreign stock returns. Applied Economics Letters. [Cited by 2] (0.26/year)
- SCHWARTZ, R.A. and D.K. WHITCOMB, 1977. The Time-Variance Relationship: Evidence on Autocorrelation in Common Stock Returns. The Journal of Finance. [Cited by 7] (0.24/year)
- FERRY, D.K., 1980. Long-Time Tail of the Autocorrelation Function for Electron Drift in High Electric Fields in Silicon. Physical Review Letters. [Cited by 6] (0.23/year)
- GU, A.Y., 2001. Index Size, Autocorrelation and Evolution of Market Efficiency. Academy of Accounting and Financial Studies Journal. [Cited by 1] (0.22/year)
- MCINISH, T.H. and R.A. WOOD, 1988. Market Frictions, Market Microstructure, Imperfect Decision Making and the Autocorrelation of …. [Cited by 3] (0.17/year)
- CONNOLLY, R. and C. STIVERS, 1999. Conditional Return Autocorrelation and Price Formation: Evidence from Six Major Equity Markets. [Cited by 1] (0.15/year)
- MCNEIL, J.A. and C.E. PRICE, 1994. Autocorrelation times for the N-fold-way Monte Carlo algorithm. PHYSICAL REVIEW-SERIES B-. [Cited by 1] (0.09/year)
- SAFVENBLAD, P., lip;. Learning the True Index Level: Index Return Autocorrelation in an ree Market. Working Paper No. 190, Working Paper Series in Economics and &h. [Cited by 1] (?/year)
[intraday returns]
There is substantial positive dependence among intraday absolute returns, which occurs at many low lags and also among returns separated by an integer number of days.
Taylor (2005)
[daily returns]
"Second, the autocorrelations of returns are all close to zero. [...]
Third, the autocorrelations of both absolute returns and squared returns are positive for many lags and they indicate substantially more linear dependence than the autocorrelations or returns."
Taylor (2005), page 93
[daily returns]
- There is almost no correlation between returns for different days.
- There is positive dependence between absolute returns on nearby days, and likewise for squared returns."
Taylor (2005), various
[intraday returns]
Intraday returns from traded assets are almost uncorrelated, with any important dependence usually restricted to a negative correlation between consecutive returns.
Taylor (2005)
- TAYLOR, S.J., 2005. Asset price dynamics, volatility, and prediction. Princeton University Press. [not cited] (0/year)
